Physical Layer Authentication in Wireless Networks-Based Machine Learning Approaches

Area of Science:

• Computer Science
• Electrical Engineering
• Information Security

Background:

• Wireless network security is critical due to rapid development and increasing threats.
• Physical layer authentication (PLA) offers information-theory security and low complexity by leveraging unique device features.
• A systematic overview of current PLA techniques and foundational principles is lacking.

Purpose of the Study:

• To systematically review and compare existing studies on physical layer authentication (PLA).
• To evaluate the impact of machine learning (ML) and deep learning (DL) on PLA security performance in wireless networks.
• To identify current challenges and propose future research directions in PLA.

Main Methods:

• Systematic literature review and comparative analysis of existing PLA studies.
• Evaluation of ML and DL techniques applied to PLA models.
• Identification of key features and methodologies in PLA research.

Main Results:

• Machine learning and deep learning approaches significantly enhance wireless network security performance in PLA models.
• A comprehensive comparison of various PLA techniques and their effectiveness is presented.
• The study demonstrates the latest advancements and methodologies in PLA.

Conclusions:

• PLA is a crucial component for robust wireless network security.
• ML and DL are pivotal in advancing PLA capabilities for enhanced security.
• Further research is needed to address identified issues and optimize PLA for future wireless systems.